Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     digital
    -0.07
     behavioral
    -0.06
     oral
    -0.06
    προ
    -0.06
    (loop
    -0.06
     booty
    -0.06
    xde
    -0.06
    unit
    -0.06
     GC
    -0.06
    (topic
    -0.06
    POSITIVE LOGITS
     midst
    0.08
    :Add
    0.07
    クロ
    0.07
     ceny
    0.06
    ember
    0.06
    イヤ
    0.06
    venes
    0.06
    olph
    0.06
     Deleted
    0.06
    Currently
    0.06
    Act Density 0.009%

    No Known Activations